BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260404T094330EDT-9890JKbnWs@132.216.98.100
DTSTAMP:20260404T134330Z
DESCRIPTION:Title: ML foundations\; Harmonic analysis & group representatio
 n theory\n\nAbstract: Lie group equivariant networks have become the stand
 ard framework for modeling molecular systems and many systems of partial d
 ifferential equations with neural networks\, as well as a range of tasks i
 n robotics and 3D vision. At the same time\, equivariance to permutations 
 has emerged as the crucial constraint in some other problems\, specificall
 y graph neural networks. In this talk I will present the general mathemati
 cal theory that encompasses equivariance to both the continuous and discre
 te symmetries\, contrast the two settings\, and specifically discuss the i
 nteraction between them in problems that possess both types of symmetry. I
  will talk about recent work on higher order permutation equivariance in g
 raph neural networks\, and specifically discuss computational aspects of i
 mplementing equivariant networks.\n
DTSTART:20250828T140000Z
DTEND:20250828T151500Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Risi Kondor (University of Chicago)
URL:https://www.mcgill.ca/mathstat/channels/event/risi-kondor-university-ch
 icago-366841
END:VEVENT
END:VCALENDAR